SOTAVerified

Reinforcement Learning (RL)

Reinforcement Learning (RL) involves training an agent to take actions in an environment to maximize a cumulative reward signal. The agent interacts with the environment and learns by receiving feedback in the form of rewards or punishments for its actions. The goal of reinforcement learning is to find the optimal policy or decision-making strategy that maximizes the long-term reward.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 551–560 of 15113 papers

TitleStatusHype
Policy-Based Radiative Transfer: Solving the 2-Level Atom Non-LTE Problem using Soft Actor-Critic Reinforcement Learning—0
SARI: Structured Audio Reasoning via Curriculum-Guided Reinforcement Learning—0
StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation—0
Insights from Verification: Training a Verilog Generation LLM with Reinforcement Learning with Testbench Feedback—0
LAPP: Large Language Model Feedback for Preference-Driven Reinforcement Learning—0
Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL—0
Learning to Reason under Off-Policy GuidanceCode3
OTC: Optimal Tool Calls via Reinforcement Learning—0
FlowReasoner: Reinforcing Query-Level Meta-AgentsCode2
Dynamic Contrastive Skill Learning with State-Transition Based Skill Clustering and Dynamic Length Adjustment—0
Show:102550
← PrevPage 56 of 1512Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PPGMean Normalized Performance0.76—Unverified
2PPOMean Normalized Performance0.58—Unverified